ai 7.0.58 → 7.0.60

package/CHANGELOG.md

@@ -1,5 +1,22 @@
 # ai
 
+## 7.0.60
+
+### Patch Changes
+
+- 79c52ef: Align `ToolLoopAgent` `prepareCall` types with the settings available and honored at runtime.
+- Updated dependencies [3cc1bb6]
+  - @ai-sdk/gateway@4.0.48
+
+## 7.0.59
+
+### Patch Changes
+
+- Updated dependencies [401a4ba]
+- Updated dependencies [7af9646]
+  - @ai-sdk/provider-utils@5.0.26
+  - @ai-sdk/gateway@4.0.47
+
 ## 7.0.58
 
 ### Patch Changes

package/dist/index.d.ts

@@ -5122,9 +5122,9 @@ type ToolLoopAgentSettings<CALL_OPTIONS = never, TOOLS extends ToolSet = {}, RUN
      *   }),
      * ```
      */
-    prepareCall?: (options: Omit<AgentCallParameters<CALL_OPTIONS, NoInfer<TOOLS>, NoInfer<RUNTIME_CONTEXT>>, 'onStepEnd' | 'onStepFinish'> & Pick<ToolLoopAgentSettings<CALL_OPTIONS, TOOLS, RUNTIME_CONTEXT, NoInfer<OUTPUT>>, 'model' | 'tools' | 'maxOutputTokens' | 'temperature' | 'topP' | 'topK' | 'presencePenalty' | 'frequencyPenalty' | 'stopSequences' | 'seed' | 'reasoning' | 'headers' | 'instructions' | 'allowSystemInMessages' | 'stopWhen' | 'telemetry' | 'experimental_telemetry' | 'activeTools' | 'toolOrder' | 'toolApproval' | 'experimental_toolCallers' | 'providerOptions' | 'experimental_download' | 'experimental_refineToolInput' | 'include' | 'runtimeContext' | '_internal'> & {
+    prepareCall?: (options: Omit<AgentCallParameters<CALL_OPTIONS, NoInfer<TOOLS>, NoInfer<RUNTIME_CONTEXT>>, 'abortSignal' | 'timeout' | 'onStart' | 'experimental_onStart' | 'onStepStart' | 'experimental_onStepStart' | 'onToolExecutionStart' | 'onToolExecutionEnd' | 'onStepEnd' | 'onStepFinish' | 'onEnd' | 'onFinish'> & Pick<ToolLoopAgentSettings<CALL_OPTIONS, TOOLS, RUNTIME_CONTEXT, NoInfer<OUTPUT>>, 'model' | 'tools' | 'toolChoice' | 'maxRetries' | 'maxOutputTokens' | 'temperature' | 'topP' | 'topK' | 'presencePenalty' | 'frequencyPenalty' | 'stopSequences' | 'seed' | 'reasoning' | 'headers' | 'instructions' | 'allowSystemInMessages' | 'stopWhen' | 'telemetry' | 'experimental_telemetry' | 'activeTools' | 'toolOrder' | 'toolApproval' | 'experimental_toolCallers' | 'prepareStep' | 'repairToolCall' | 'experimental_repairToolCall' | 'providerOptions' | 'experimental_download' | 'experimental_refineToolInput' | 'include' | 'runtimeContext' | '_internal'> & {
         toolsContext: InferToolSetContext<TOOLS>;
-    }) => MaybePromiseLike<Pick<ToolLoopAgentSettings<CALL_OPTIONS, TOOLS, RUNTIME_CONTEXT, NoInfer<OUTPUT>>, 'model' | 'tools' | 'maxOutputTokens' | 'temperature' | 'topP' | 'topK' | 'presencePenalty' | 'frequencyPenalty' | 'stopSequences' | 'seed' | 'reasoning' | 'headers' | 'instructions' | 'allowSystemInMessages' | 'stopWhen' | 'telemetry' | 'experimental_telemetry' | 'activeTools' | 'toolOrder' | 'toolApproval' | 'experimental_toolCallers' | 'providerOptions' | 'experimental_download' | 'experimental_refineToolInput' | 'include' | 'runtimeContext' | '_internal'> & Omit<Prompt, 'system'> & {
+    }) => MaybePromiseLike<Pick<ToolLoopAgentSettings<CALL_OPTIONS, TOOLS, RUNTIME_CONTEXT, NoInfer<OUTPUT>>, 'model' | 'tools' | 'toolChoice' | 'maxRetries' | 'maxOutputTokens' | 'temperature' | 'topP' | 'topK' | 'presencePenalty' | 'frequencyPenalty' | 'stopSequences' | 'seed' | 'reasoning' | 'headers' | 'instructions' | 'allowSystemInMessages' | 'stopWhen' | 'telemetry' | 'experimental_telemetry' | 'activeTools' | 'toolOrder' | 'toolApproval' | 'experimental_toolCallers' | 'prepareStep' | 'repairToolCall' | 'experimental_repairToolCall' | 'providerOptions' | 'experimental_download' | 'experimental_refineToolInput' | 'include' | 'runtimeContext' | '_internal'> & Omit<Prompt, 'system'> & {
         toolsContext: InferToolSetContext<TOOLS>;
     }>;
 };

package/dist/index.js

@@ -1143,7 +1143,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.58" : "0.0.0-test";
+var VERSION = true ? "7.0.60" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/internal/index.js

@@ -92,7 +92,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.58" : "0.0.0-test";
+var VERSION = true ? "7.0.60" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/docs/03-ai-sdk-harnesses/02-harness-agent.mdx

@@ -364,7 +364,8 @@ console.log(preparation.identity);
 - `harness`: the adapter instance.
 - `sandbox`: a `HarnessV1SandboxProvider`.
 - `id`: optional stable agent identifier.
-- `instructions`: instructions applied once to a fresh session.
+- `instructions`: instructions appended to the runtime's system or developer
+  prompt when supported, or prepended to the first user prompt otherwise.
 - `stopWhen`: condition(s) for finishing a result slice after a completed
   harness tool step that can continue into another model step.
 - `tools`: AI SDK tools executed by the host when the harness calls them.

package/docs/03-ai-sdk-harnesses/03-tools.mdx

@@ -5,11 +5,13 @@ description: Use tools with AI SDK harnesses.
 
 # Harness Tools
 
-Harnesses have two tool surfaces:
+Harnesses have three tool surfaces:
 
 - Built-in tools exposed by the underlying harness runtime, such as file reads,
   edits, shell commands, and web search.
 - AI SDK tools that you pass to `HarnessAgent` with the `tools` setting.
+- External MCP tools configured through the harness adapter's `mcpServers`
+  setting.
 
 This page covers harness-specific behavior. For general AI SDK tool concepts,
 schemas, tool results, and `tool()` usage, see [Tools](/docs/foundations/tools).

package/docs/06-advanced/02-stopping-streams.mdx

@@ -44,7 +44,7 @@ export async function POST(req: Request) {
 ## AI SDK UI
 
 The hooks, e.g. `useChat` or `useCompletion`, provide a `stop` helper function that can be used to cancel a stream.
-This will cancel the stream from the client side to the server.
+This aborts the HTTP request from the client. To also stop the model request on the server, your server runtime must propagate the client disconnect to the request's `AbortSignal`, and your route must forward that signal to the AI SDK Core call as shown above.
 
 <Note type="warning">
   Stream abort functionality is not compatible with stream resumption. If you're
@@ -78,6 +78,27 @@ export default function Chat() {
 }
 ```
 
+### Vercel
+
+On Vercel, [request cancellation](https://vercel.com/docs/functions/functions-api-reference#cancel-requests) is only supported in the Node.js runtime and must be enabled for each function that needs it. Add `supportsCancellation` to the function's configuration in `vercel.json`:
+
+```json filename="vercel.json"
+{
+  "functions": {
+    "app/api/chat/route.ts": {
+      "supportsCancellation": true
+    }
+  }
+}
+```
+
+With cancellation enabled, calling `stop()` aborts the client request, Vercel aborts `req.signal`, and forwarding `req.signal` as `abortSignal` cancels the model request.
+
+<Note type="warning">
+  Without `supportsCancellation`, `stop()` still stops the client-side stream
+  but the server-side generation may continue.
+</Note>
+
 ## Handling stream abort cleanup
 
 When streams are aborted, you may need to perform cleanup operations such as persisting partial results or cleaning up resources. The `onAbort` callback provides a way to handle these scenarios on the server side.

package/docs/06-advanced/04-caching.mdx

@@ -120,9 +120,7 @@ You can see a full example of caching with Redis in a Next.js application in our
 
 Alternatively, each AI SDK Core function has special lifecycle callbacks you can use. The one of interest is likely `onEnd`, which is called when the generation is complete. This is where you can cache the full response.
 
-Here's an example of how you can implement caching using Vercel KV and Next.js to cache the OpenAI response for 1 hour:
-
-This example uses [Upstash Redis](https://upstash.com/docs/redis/overall/getstarted) and Next.js to cache the response for 1 hour.
+Here's an example of how you can use [Upstash Redis](https://upstash.com/redis) and Next.js to cache the OpenAI response for 1 hour:
 
 ```tsx filename="app/api/chat/route.ts"
 import {

package/docs/06-advanced/06-rate-limiting.mdx

@@ -11,13 +11,11 @@ specified timeframe. This simple technique acts as a gatekeeper,
 preventing excessive usage that can degrade service performance and incur
 unnecessary costs.
 
-## Rate Limiting with Vercel KV and Upstash Ratelimit
+## Rate Limiting with Upstash Redis and Upstash Ratelimit
 
-In this example, you will protect an API endpoint using [Vercel KV](https://vercel.com/storage/kv)
-and [Upstash Ratelimit](https://github.com/upstash/ratelimit).
+In this example, you will protect an API endpoint using [Upstash Redis](https://upstash.com/redis) and [Upstash Ratelimit](https://github.com/upstash/ratelimit).
 
 ```tsx filename='app/api/generate/route.ts'
-import kv from '@vercel/kv';
 import {
   createUIMessageStreamResponse,
   streamText,
@@ -25,6 +23,7 @@ import {
 } from 'ai';
 __PROVIDER_IMPORT__;
 import { Ratelimit } from '@upstash/ratelimit';
+import { Redis } from '@upstash/redis';
 import { NextRequest } from 'next/server';
 
 // Allow streaming responses up to 30 seconds
@@ -32,7 +31,7 @@ export const maxDuration = 30;
 
 // Create Rate limit
 const ratelimit = new Ratelimit({
-  redis: kv,
+  redis: Redis.fromEnv(),
   limiter: Ratelimit.fixedWindow(5, '30s'),
 });
 
@@ -61,6 +60,6 @@ export async function POST(req: NextRequest) {
 
 ## Simplify API Protection
 
-With Vercel KV and Upstash Ratelimit, it is possible to protect your APIs
+With Upstash Redis and Upstash Ratelimit, it is possible to protect your APIs
 from such attacks with ease. To learn more about how Ratelimit works and
 how it can be configured to your needs, see [Ratelimit Documentation](https://upstash.com/docs/oss/sdks/ts/ratelimit/overview).

package/docs/06-advanced/10-vercel-deployment-guide.mdx

@@ -95,6 +95,47 @@ export const maxDuration = 30;
 
 You can increase the max duration to 60 seconds on the Hobby Tier. For other tiers, [see the documentation](https://vercel.com/docs/functions/runtimes#max-duration) for limits.
 
+### Request Cancellation
+
+AI SDK UI helpers such as `useChat` and `useCompletion` abort the client request when you call `stop()`. To propagate that cancellation to a Vercel Function and its model request, you must:
+
+1. Use the Node.js runtime, which is the default for Next.js route handlers.
+2. Enable [`supportsCancellation`](https://vercel.com/docs/functions/functions-api-reference#cancel-requests) for the route in `vercel.json`.
+3. Forward the route's `req.signal` to `streamText` or `generateText` as `abortSignal`.
+
+For example, enable cancellation for your chat route:
+
+```json filename="vercel.json"
+{
+  "functions": {
+    "app/api/chat/route.ts": {
+      "supportsCancellation": true
+    }
+  }
+}
+```
+
+Then forward the request signal to the AI SDK:
+
+```ts filename="app/api/chat/route.ts" highlight="10"
+import { convertToModelMessages, streamText, type UIMessage } from 'ai';
+__PROVIDER_IMPORT__;
+
+export async function POST(req: Request) {
+  const { messages }: { messages: UIMessage[] } = await req.json();
+
+  const result = streamText({
+    model: __MODEL__,
+    messages: convertToModelMessages(messages),
+    abortSignal: req.signal,
+  });
+
+  return result.toUIMessageStreamResponse();
+}
+```
+
+Without `supportsCancellation`, calling `stop()` closes the client-side stream but does not cancel the Vercel Function or model request. See [Stopping Streams](/docs/advanced/stopping-streams) for the complete client and server setup.
+
 ## Security Considerations
 
 Given the high cost of calling an LLM, it's important to have measures in place that can protect your application from abuse.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.58",
+  "version": "7.0.60",
   "type": "module",
   "description": "AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.",
   "license": "Apache-2.0",
@@ -42,9 +42,9 @@
     }
   },
   "dependencies": {
+    "@ai-sdk/gateway": "4.0.48",
     "@ai-sdk/provider": "4.0.7",
-    "@ai-sdk/provider-utils": "5.0.25",
-    "@ai-sdk/gateway": "4.0.46"
+    "@ai-sdk/provider-utils": "5.0.26"
   },
   "devDependencies": {
     "@edge-runtime/vm": "^5.0.0",

package/src/agent/tool-loop-agent-settings.ts

@@ -307,7 +307,18 @@ export type ToolLoopAgentSettings<
           NoInfer<TOOLS>,
           NoInfer<RUNTIME_CONTEXT>
         >,
-        'onStepEnd' | 'onStepFinish'
+        | 'abortSignal'
+        | 'timeout'
+        | 'onStart'
+        | 'experimental_onStart'
+        | 'onStepStart'
+        | 'experimental_onStepStart'
+        | 'onToolExecutionStart'
+        | 'onToolExecutionEnd'
+        | 'onStepEnd'
+        | 'onStepFinish'
+        | 'onEnd'
+        | 'onFinish'
       > &
         Pick<
           ToolLoopAgentSettings<
@@ -318,6 +329,8 @@ export type ToolLoopAgentSettings<
           >,
           | 'model'
           | 'tools'
+          | 'toolChoice'
+          | 'maxRetries'
           | 'maxOutputTokens'
           | 'temperature'
           | 'topP'
@@ -337,6 +350,9 @@ export type ToolLoopAgentSettings<
           | 'toolOrder'
           | 'toolApproval'
           | 'experimental_toolCallers'
+          | 'prepareStep'
+          | 'repairToolCall'
+          | 'experimental_repairToolCall'
           | 'providerOptions'
           | 'experimental_download'
           | 'experimental_refineToolInput'
@@ -354,6 +370,8 @@ export type ToolLoopAgentSettings<
         >,
         | 'model'
         | 'tools'
+        | 'toolChoice'
+        | 'maxRetries'
         | 'maxOutputTokens'
         | 'temperature'
         | 'topP'
@@ -373,6 +391,9 @@ export type ToolLoopAgentSettings<
         | 'toolOrder'
         | 'toolApproval'
         | 'experimental_toolCallers'
+        | 'prepareStep'
+        | 'repairToolCall'
+        | 'experimental_repairToolCall'
         | 'providerOptions'
         | 'experimental_download'
         | 'experimental_refineToolInput'